-------------------------------------------------------------------------------help parmcip_opts(Roger Newson) -------------------------------------------------------------------------------

Options formetaparmandparmcip

Syntax

optionsDescription -------------------------------------------------------------------------notdistUse Normal ort-distributioneformEstimates and confidence limits exponentiatedfloatNumeric output variables of typefloator lessfastCalculate confidence limits without precautionsestimate(varname)Name of input estimate variablestderr(varname)Name of input standard error variabledof(varname)Name of input degrees of freedom variablezstat(newvarname)Name of outputz-statistic variabletstat(newvarname)Name of outputt-statistic variablepvalue(newvarname)Name of outputP-value variablestars(numlist)List ofP-value thresholds for starsnstars(newvarname)Name of output stars variablelevel(numlist)Confidence level(s) for calculating confidence limitsclnumber(numbering_rule)Numbering rule for naming confidence limit variablesminprefix(prefix)Prefix for lower confidence limitsmaxprefix(prefix)Prefix for upper confidence limitsreplaceReplace variables with same names as output variables -------------------------------------------------------------------------where

numbering_ruleis

level|rank

DescriptionThese options are available for

metaparmand forparmcip. They control the calculation of confidence limits andP-values. They are not often used, asmetaparmandparmciphave defaults for these options, which are usually sensible.

Optionsnotdistspecifies whether or not at-distribution is used to calculate confidence limits. Iftdistis specified, then at-distribution is used. Ifnotdistis specified, then a standard Normal distribution is used. If neithertdistnornotdistis specified by the user, then the option is set totdistif thedof()option is set to the name of an existing variable, and is set tonotdistotherwise. Iftdistis specified withmetaparm, then the degrees of freedom in the output dataset are calculated from the degrees of freedom and standard errors in the input dataset, using the Satterthwaite formula (Satterthwaite, 1946).

eformindicates that the input estimates are exponentiated, and that the input standard errors are multiplied by the exponentiated estimate, and that the output confidence limits are to be exponentiated. Ifeformis used withmetaparm, then the estimate variable in the output dataset is exponentiated, and the standard error variable in the output dataset is multiplied by the exponentiated estimate variable.

floatspecifies that the numeric output variables will be created as typefloator below. Iffloatis unset, then the numeric output variables are created as typedouble. Note that all generated variables are compressed as much as possible without loss of information, whether or notfloatis specified.

fastis an option for programmers, and specifies that no action will be taken to restore the original data if the user presses Break. If used withmetaparm, thefastoption implies thenorestoreoption (seemetaparm_outdest_opts).

estimate(varname)specifies the name of the input variable containing estimates. It is set toestimateif not specified.

stderr(varname)specifies the name of the input variable containing standard errors. It is set tostderrif not specified.

dof(varname)specifies the name of the input variable containing degrees of freedom. It is set todofif not specified.

zstat(newvarname)specifies the name of the output variable containing thez-statistics. It is set tozif not specified.

tstat(newvarname)specifies the name of the output variable containing thet-statistics. It is set totif not specified.

pvalue(newvarname)specifies the name of the output variable containing theP-values. It is set topif not specified.

stars(numlist)is used to generate a string variable with default namestars, containing the stars for theP-values. It works in the same way as thestars()option ofparmest.

nstars(newvarname)specifies the name of the output variable containing the stars, ifstars()is specified. Ifnstars()is not specified, then the name is set tostars.

level(numlist)specifies the confidence levels, in percent, for the confidence limit variables created in the output dataset. It works in the same way as thelevel()option ofparmest.

clnumber(numbering_rule)specifies the rule used to number the names of the confidence limit variables created in the output dataset. It works similarly to theclnumber()option ofparmest. However, withparmcipandmetaparm, the user may specify prefixes other thanminandmaxfor the confidence limits, using theminprefix()andmaxprefix()options.

minprefix(prefix)specifies the prefix used for naming the lower confidence limit variables. It is set tominif not specified. For instance, if the user specifiesminprefix(inf), then the lower 95% confidence limit variable will be namedinf95.

maxprefix(prefix)specifies the prefix used for naming the upper confidence limit variables. It is set tomaxif not specified. For instance, if the user specifiesmaxprefix(sup), then the upper 95% confidence limit variable will be namedsup95.

replaceis aparmcipoption, ignored bymetaparm. It specifies that, if there are existing variables in the input dataset with the same names as the generated variables specified by thezstat(),tstat(),pvalue(),clnumber(),minprefix()ormaxprefix()options, then those variables will be replaced. Whether or notreplaceis specified, the names of the output variables are not allowed to clash with each other, with the input variables, or with the variables in theby()andsumvar()options ofmetaparm.

AuthorRoger Newson, Imperial College London, UK. Email: r.newson@imperial.ac.uk

ReferencesSatterthwaite, F. E. 1946. An approximate distribution of estimates of variance components.

Biometrics Bulletin2(6): 110-114.

Also seeManual:

[U] 20 Estimation and postestimation commandsOn-line: help for estcom help forparmest,parmby,parmcip,metaparm,metaparm_outdest_opts,metaparm_content_opts,metaparm_resultssets,parmest_resultssets